© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18235
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessness
    -0.10
    ä¸Ģå¿ĥ
    -0.09
    æĹ¥å¸¸
    -0.09
    uele
    -0.09
    olvable
    -0.09
    符åı·
    -0.09
    etting
    -0.09
    VICES
    -0.09
    åĩºèĩª
    -0.08
    Lik
    -0.08
    POSITIVE LOGITS
    éĻĤ
    0.11
    èĢĮçİ°åľ¨
    0.10
    è¿ľæ´ĭ
    0.09
    çĶ¥
    0.09
    éĤ®è½®
    0.09
    æ»ŀ
    0.09
    å½ĵåľ°æŶéĹ´
    0.09
    è¿Ļ段
    0.08
     partition
    0.08
    é£İæ°´
    0.08
    Activations Density 0.145%

    No Known Activations